summaryrefslogtreecommitdiff
path: root/Build/source/texk/web2c/luatexdir/font/tounicode.c
blob: ecac8112e5c929de4c1ddcc94f5365341de48b6b (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
/* tounicode.c
   Copyright 2006 Han The Thanh, <thanh@pdftex.org>
   Copyright 2006-2008 Taco Hoekwater <taco@luatex.org>

   This file is part of LuaTeX.

   LuaTeX is free software; you can redistribute it and/or modify it under
   the terms of the GNU General Public License as published by the Free
   Software Foundation; either version 2 of the License, or (at your
   option) any later version.

   LuaTeX is distributed in the hope that it will be useful, but WITHOUT
   ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
   FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public
   License for more details.

   You should have received a copy of the GNU General Public License along
   with LuaTeX; if not, see <http://www.gnu.org/licenses/>. */

#include "ptexlib.h"

static const char _svn_version[] =
    "$Id: tounicode.c 2448 2009-06-08 07:43:50Z taco $ $URL: http://foundry.supelec.fr/svn/luatex/tags/beta-0.40.3/source/texk/web2c/luatexdir/font/tounicode.c $";

#define isXdigit(c) (isdigit(c) || ('A' <= (c) && (c) <= 'F'))
#define UNI_UNDEF          -1
#define UNI_STRING         -2   /* string allocated by def_tounicode() */
#define UNI_EXTRA_STRING   -3   /* string allocated by set_glyph_unicode() */

static struct avl_table *glyph_unicode_tree = NULL;

static int comp_glyph_unicode_entry(const void *pa, const void *pb, void *p)
{
    (void) p;
    return strcmp(((const glyph_unicode_entry *) pa)->name,
                  ((const glyph_unicode_entry *) pb)->name);
}

static glyph_unicode_entry *new_glyph_unicode_entry(void)
{
    glyph_unicode_entry *e;
    e = xtalloc(1, glyph_unicode_entry);
    e->name = NULL;
    e->code = UNI_UNDEF;
    e->unicode_seq = NULL;
    return e;
}

static void destroy_glyph_unicode_entry(void *pa, void *pb)
{
    glyph_unicode_entry *e = (glyph_unicode_entry *) pa;
    (void) pb;
    xfree(e->name);
    if (e->code == UNI_STRING) {
        assert(e->unicode_seq != NULL);
        xfree(e->unicode_seq);
    }
}

void glyph_unicode_free(void)
{
    if (glyph_unicode_tree != NULL)
        avl_destroy(glyph_unicode_tree, destroy_glyph_unicode_entry);
}

void def_tounicode(str_number glyph, str_number unistr)
{
    char buf[SMALL_BUF_SIZE], *p;
    char buf2[SMALL_BUF_SIZE], *q;
    int valid_unistr;           /* 0: invalid; 1: unicode value; 2: string */
    int i, l;
    glyph_unicode_entry *gu, t;
    void **aa;

    p = makecstring(glyph);
    assert(strlen(p) < SMALL_BUF_SIZE);
    strcpy(buf, p);             /* copy the result to buf before next call of makecstring() */
    p = makecstring(unistr);
    while (*p == ' ')
        p++;                    /* ignore leading spaces */
    l = strlen(p);
    while (l > 0 && p[l - 1] == ' ')
        l--;                    /* ignore traling spaces */
    valid_unistr = 1;           /* a unicode value is the most common case */
    for (i = 0; i < l; i++) {
        if (p[i] == ' ')
            valid_unistr = 2;   /* if a space occurs we treat this entry as a string */
        else if (!isXdigit(p[i])) {
            valid_unistr = 0;
            break;
        }
    }
    if (l == 0 || valid_unistr == 0 || strlen(buf) == 0
        || strcmp(buf, notdef) == 0) {
        pdftex_warn("ToUnicode: invalid parameter(s): `%s' => `%s'", buf, p);
        return;
    }
    if (glyph_unicode_tree == NULL) {
        glyph_unicode_tree =
            avl_create(comp_glyph_unicode_entry, NULL, &avl_xallocator);
        assert(glyph_unicode_tree != NULL);
    }
    t.name = buf;
    /* allow overriding existing entries */
    if ((gu = (glyph_unicode_entry *) avl_find(glyph_unicode_tree, &t)) != NULL) {
        if (gu->code == UNI_STRING) {
            assert(gu->unicode_seq != NULL);
            xfree(gu->unicode_seq);
        }
    } else {                    /* make new entry */
        gu = new_glyph_unicode_entry();
        gu->name = xstrdup(buf);
    }
    if (valid_unistr == 2) {    /* a string with space(s) */
        /* copy p to buf2, ignoring spaces */
        for (q = buf2; *p != 0; p++)
            if (*p != ' ')
                *q++ = *p;
        *q = 0;
        gu->code = UNI_STRING;
        gu->unicode_seq = xstrdup(buf2);
    } else {
        i = sscanf(p, "%lX", &(gu->code));
        assert(i == 1);
    }
    aa = avl_probe(glyph_unicode_tree, gu);
    assert(aa != NULL);
}


static long check_unicode_value(char *s, boolean multiple_value)
{
    int l = strlen(s);
    int i;
    long code;

    if (l == 0)
        return UNI_UNDEF;
    if (multiple_value && l % 4 != 0)
        return UNI_UNDEF;
    if (!multiple_value && !(4 <= l && l <= 6))
        return UNI_UNDEF;

    for (i = 0; i < l; i++) {
        if (!isXdigit(s[i]))
            return UNI_UNDEF;
        if (multiple_value) {
            if (i % 4 == 3) {
                if (sscanf(s + i - 3, "%4lX", &code) != 1)
                    return UNI_UNDEF;
                if (!((0x0000 <= code && code <= 0xD7FF) ||
                      (0xE000 <= code && code <= 0xFFFF)))
                    return UNI_UNDEF;
            }
        } else {                /* single value */
            if (i == l - 1) {
                if (sscanf(s, "%lX", &code) != 1)
                    return UNI_UNDEF;
                if (!((0x0000 <= code && code <= 0xD7FF) ||
                      (0xE000 <= code && code <= 0x10FFFF)))
                    return UNI_UNDEF;
            }
        }
    }
    return code;
}

static char *utf16be_str(long code)
{
    static char buf[SMALL_BUF_SIZE];
    long v;
    unsigned vh, vl;

    assert(code >= 0);

    if (code <= 0xFFFF)
        sprintf(buf, "%04lX", code);
    else {
        v = code - 0x10000;
        vh = v / 0x400 + 0xD800;
        vl = v % 0x400 + 0xDC00;
        sprintf(buf, "%04X%04X", vh, vl);
    }
    return buf;
}


/* this function set proper values to *gp based on s; in case it returns
 * gp->code == UNI_EXTRA_STRING then the caller is responsible for freeing
 * gp->unicode_seq too */
static void set_glyph_unicode(char *s, glyph_unicode_entry * gp)
{
    char buf[SMALL_BUF_SIZE], buf2[SMALL_BUF_SIZE], *p;
    long code;
    boolean last_component;
    glyph_unicode_entry tmp, *ptmp;

    /* skip dummy entries */
    if (s == NULL || s == notdef)
        return;

    /* strip everything after the first dot */
    p = strchr(s, '.');
    if (p != NULL) {
        *buf = 0;
        strncat(buf, s, p - s);
        s = buf;
    }

    if (strlen(s) == 0)
        return;

    /* check for case of multiple components separated by '_' */
    p = strchr(s, '_');
    if (p != NULL) {
        assert(strlen(s) < sizeof(buf));
        if (s != buf) {
            strcpy(buf, s);
            p = strchr(buf, '_');
            s = buf;
        }
        *buf2 = 0;
        last_component = false;
        for (;;) {
            *p = 0;
            tmp.code = UNI_UNDEF;
            set_glyph_unicode(s, &tmp);
            switch (tmp.code) {
            case UNI_UNDEF:    /* not found, do nothing */
                break;
            case UNI_STRING:   /* s matched an entry with string value in the database */
                assert(tmp.unicode_seq != NULL);
                assert(strlen(buf2) + strlen(tmp.unicode_seq) < sizeof(buf2));
                strcat(buf2, tmp.unicode_seq);
                break;
            case UNI_EXTRA_STRING:     /* s is a multiple value of form "uniXXXX" */
                assert(strlen(buf2) + strlen(tmp.unicode_seq) < sizeof(buf2));
                strcat(buf2, tmp.unicode_seq);
                xfree(tmp.unicode_seq);
                break;
            default:           /* s matched an entry with numeric value in the
                                   database, or a value derived from "uXXXX" */
                assert(tmp.code >= 0);
                strcat(buf2, utf16be_str(tmp.code));
            }
            if (last_component)
                break;
            s = p + 1;
            p = strchr(s, '_');
            if (p == NULL) {
                p = strend(s);
                last_component = true;
            }
        }
        gp->code = UNI_EXTRA_STRING;
        gp->unicode_seq = xstrdup(buf2);
        return;
    }

    /* lookup for glyph name in the database */
    tmp.name = s;
    tmp.code = UNI_UNDEF;
    ptmp = (glyph_unicode_entry *) avl_find(glyph_unicode_tree, &tmp);
    if (ptmp != NULL) {
        gp->code = ptmp->code;
        gp->unicode_seq = ptmp->unicode_seq;
        return;
    }

    /* check for case of "uniXXXX" (multiple 4-hex-digit values allowed) */
    if (str_prefix(s, "uni")) {
        p = s + strlen("uni");
        code = check_unicode_value(p, true);
        if (code != UNI_UNDEF) {
            if (strlen(p) == 4) /* single value */
                gp->code = code;
            else {              /* multiple value */
                gp->code = UNI_EXTRA_STRING;
                gp->unicode_seq = xstrdup(p);
            }
        }
        return;                 /* since the last case cannot happen */
    }

    /* check for case of "uXXXX" (single value up to 6 hex digits) */
    if (str_prefix(s, "u")) {
        p = s + strlen("u");
        code = check_unicode_value(p, false);
        if (code != UNI_UNDEF) {
            assert(code >= 0);
            gp->code = code;
        }
    }
}

static void set_cid_glyph_unicode(long index, glyph_unicode_entry * gp,
                                  internal_font_number f)
{
    char *s;
    if (font_tounicode(f) &&
        (s = get_charinfo_tounicode(char_info(f, index))) != NULL) {
        gp->code = UNI_EXTRA_STRING;
        gp->unicode_seq = xstrdup(s);
    } else {
        gp->code = index;       /* fallback */
    }
}


integer write_tounicode(char **glyph_names, char *name)
{
    char buf[SMALL_BUF_SIZE], *p;
    static char builtin_suffix[] = "-builtin";
    short range_size[257];
    glyph_unicode_entry gtab[257];
    integer objnum;
    int i, j;
    int bfchar_count, bfrange_count, subrange_count;
    assert(strlen(name) + strlen(builtin_suffix) < SMALL_BUF_SIZE);
    if (glyph_unicode_tree == NULL) {
        /*pdftex_warn("no GlyphToUnicode entry has been inserted yet!"); */
        fixed_gen_tounicode = 0;
        return 0;
    }
    strcpy(buf, name);
    if ((p = strrchr(buf, '.')) != NULL && strcmp(p, ".enc") == 0)
        *p = 0;                 /* strip ".enc" from encoding name */
    else
        strcat(buf, builtin_suffix);    /* ".enc" not present, this is a builtin
                                           encoding so the name is eg "cmr10-builtin" */
    objnum = pdf_new_objnum();
    pdf_begin_dict(objnum, 0);
    pdf_begin_stream();
    pdf_printf("%%!PS-Adobe-3.0 Resource-CMap\n"
               "%%%%DocumentNeededResources: ProcSet (CIDInit)\n"
               "%%%%IncludeResource: ProcSet (CIDInit)\n"
               "%%%%BeginResource: CMap (TeX-%s-0)\n"
               "%%%%Title: (TeX-%s-0 TeX %s 0)\n"
               "%%%%Version: 1.000\n"
               "%%%%EndComments\n"
               "/CIDInit /ProcSet findresource begin\n"
               "12 dict begin\n"
               "begincmap\n"
               "/CIDSystemInfo\n"
               "<< /Registry (TeX)\n"
               "/Ordering (%s)\n"
               "/Supplement 0\n"
               ">> def\n"
               "/CMapName /TeX-%s-0 def\n"
               "/CMapType 2 def\n"
               "1 begincodespacerange\n"
               "<00> <FF>\n" "endcodespacerange\n", buf, buf, buf, buf, buf);

    /* set gtab */
    for (i = 0; i < 256; ++i) {
        gtab[i].code = UNI_UNDEF;
        set_glyph_unicode(glyph_names[i], &gtab[i]);
    }
    gtab[256].code = UNI_UNDEF;

    /* set range_size */
    for (i = 0; i < 256;) {
        if (gtab[i].code == UNI_STRING || gtab[i].code == UNI_EXTRA_STRING) {
            range_size[i] = 1;  /* single entry */
            i++;
        } else if (gtab[i].code == UNI_UNDEF) {
            range_size[i] = 0;  /* no entry */
            i++;
        } else {                /* gtab[i].code >= 0 */
            j = i;
            while (i < 256 && gtab[i + 1].code >= 0 &&
                   gtab[i].code + 1 == gtab[i + 1].code)
                i++;
            /* at this point i is the last entry of the subrange */
            i++;                /* move i to the next entry */
            range_size[j] = i - j;
        }
    }

    /* calculate bfrange_count and bfchar_count */
    bfrange_count = 0;
    bfchar_count = 0;
    for (i = 0; i < 256;) {
        if (range_size[i] == 1) {
            bfchar_count++;
            i++;
        } else if (range_size[i] > 1) {
            bfrange_count++;
            i += range_size[i];
        } else
            i++;
    }

    /* write out bfrange */
    i = 0;
  write_bfrange:
    if (bfrange_count > 100)
        subrange_count = 100;
    else
        subrange_count = bfrange_count;
    bfrange_count -= subrange_count;
    pdf_printf("%i beginbfrange\n", subrange_count);
    for (j = 0; j < subrange_count; j++) {
        while (range_size[i] <= 1 && i < 256)
            i++;
        assert(i < 256);
        pdf_printf("<%02X> <%02X> <%s>\n", i, i + range_size[i] - 1,
                   utf16be_str(gtab[i].code));
        i += range_size[i];
    }
    pdf_printf("endbfrange\n");
    if (bfrange_count > 0)
        goto write_bfrange;

    /* write out bfchar */
    i = 0;
  write_bfchar:
    if (bfchar_count > 100)
        subrange_count = 100;
    else
        subrange_count = bfchar_count;
    bfchar_count -= subrange_count;
    pdf_printf("%i beginbfchar\n", subrange_count);
    for (j = 0; j < subrange_count; j++) {
        while (i < 256) {
            if (range_size[i] > 1)
                i += range_size[i];
            else if (range_size[i] == 0)
                i++;
            else                /* range_size[i] == 1 */
                break;
        }
        assert(i < 256 && gtab[i].code != UNI_UNDEF);
        if (gtab[i].code == UNI_STRING || gtab[i].code == UNI_EXTRA_STRING) {
            assert(gtab[i].unicode_seq != NULL);
            pdf_printf("<%02X> <%s>\n", i, gtab[i].unicode_seq);
        } else
            pdf_printf("<%02X> <%s>\n", i, utf16be_str(gtab[i].code));
        i++;
    }
    pdf_printf("endbfchar\n");
    if (bfchar_count > 0)
        goto write_bfchar;

    /* free strings allocated by set_glyph_unicode() */
    for (i = 0; i < 256; ++i) {
        if (gtab[i].code == UNI_EXTRA_STRING)
            xfree(gtab[i].unicode_seq);
    }

    pdf_printf("endcmap\n"
               "CMapName currentdict /CMap defineresource pop\n"
               "end\n" "end\n" "%%%%EndResource\n" "%%%%EOF\n");
    pdf_end_stream();
    return objnum;
}

integer write_cid_tounicode(fo_entry * fo, internalfontnumber f)
{

    int range_size[65537];
    glyph_unicode_entry gtab[65537];
    integer objnum;
    int i, j, k;
    int bfchar_count, bfrange_count, subrange_count;
    char *buf;

    assert(fo->fd->fontname);
    buf = xmalloc(strlen(fo->fd->fontname) + 8);
    sprintf(buf, "%s-%s",
            (fo->fd->subset_tag != NULL ? fo->fd->subset_tag : "UCS"),
            fo->fd->fontname);

    objnum = pdf_new_objnum();
    pdf_begin_dict(objnum, 0);
    pdf_begin_stream();
    pdf_printf("%%!PS-Adobe-3.0 Resource-CMap\n"
               "%%%%DocumentNeededResources: ProcSet (CIDInit)\n"
               "%%%%IncludeResource: ProcSet (CIDInit)\n"
               "%%%%BeginResource: CMap (TeX-%s-0)\n"
               "%%%%Title: (TeX-%s-0 TeX %s 0)\n"
               "%%%%Version: 1.000\n"
               "%%%%EndComments\n"
               "/CIDInit /ProcSet findresource begin\n"
               "12 dict begin\n"
               "begincmap\n"
               "/CIDSystemInfo\n"
               "<< /Registry (TeX)\n"
               "/Ordering (%s)\n"
               "/Supplement 0\n"
               ">> def\n"
               "/CMapName /TeX-Identity-%s def\n"
               "/CMapType 2 def\n"
               "1 begincodespacerange\n"
               "<0000> <FFFF>\n"
               "endcodespacerange\n", buf, buf, buf, buf, buf);
    xfree(buf);
    /* set up gtab */
    for (i = 0; i < 65537; ++i) {
        gtab[i].code = UNI_UNDEF;
    }
    for (k = 1; k <= max_font_id(); k++) {
        if (k == f || -f == pdf_font_num(k)) {
            for (i = font_bc(k); i <= font_ec(k); i++) {
                if (char_exists(k, i) && char_used(k, i)) {
                    j = char_index(k, i);
                    if (gtab[j].code == UNI_UNDEF) {
                        set_cid_glyph_unicode(i, &gtab[j], f);
                    }
                }
            }
        }
    }

    /* set range_size */
    for (i = 0; i < 65536;) {
        if (gtab[i].code == UNI_STRING || gtab[i].code == UNI_EXTRA_STRING) {
            range_size[i] = 1;  /* single entry */
            i++;
        } else if (gtab[i].code == UNI_UNDEF) {
            range_size[i] = 0;  /* no entry */
            i++;
        } else {                /* gtab[i].code >= 0 */
            j = i;
            while (i < 65536 && gtab[i + 1].code >= 0 &&
                   gtab[i].code + 1 == gtab[i + 1].code)
                i++;
            /* at this point i is the last entry of the subrange */
            i++;                /* move i to the next entry */
            range_size[j] = i - j;
        }
    }

    /* calculate bfrange_count and bfchar_count */
    bfrange_count = 0;
    bfchar_count = 0;
    for (i = 0; i < 65536;) {
        if (range_size[i] == 1) {
            bfchar_count++;
            i++;
        } else if (range_size[i] > 1) {
            bfrange_count++;
            i += range_size[i];
        } else
            i++;
    }

    /* write out bfrange */
    i = 0;
  write_bfrange:
    if (bfrange_count > 100)
        subrange_count = 100;
    else
        subrange_count = bfrange_count;
    bfrange_count -= subrange_count;
    pdf_printf("%i beginbfrange\n", subrange_count);
    for (j = 0; j < subrange_count; j++) {
        while (range_size[i] <= 1 && i < 65536)
            i++;
        assert(i < 65536);
        pdf_printf("<%04X> <%04X> <%s>\n", i, i + range_size[i] - 1,
                   utf16be_str(gtab[i].code));
        i += range_size[i];
    }
    pdf_printf("endbfrange\n");
    if (bfrange_count > 0)
        goto write_bfrange;

    /* write out bfchar */
    i = 0;
  write_bfchar:
    if (bfchar_count > 100)
        subrange_count = 100;
    else
        subrange_count = bfchar_count;
    bfchar_count -= subrange_count;
    pdf_printf("%i beginbfchar\n", subrange_count);
    for (j = 0; j < subrange_count; j++) {
        while (i < 65536) {
            if (range_size[i] > 1)
                i += range_size[i];
            else if (range_size[i] == 0)
                i++;
            else                /* range_size[i] == 1 */
                break;
        }
        assert(i < 65536 && gtab[i].code != UNI_UNDEF);
        if (gtab[i].code == UNI_STRING || gtab[i].code == UNI_EXTRA_STRING) {
            assert(gtab[i].unicode_seq != NULL);
            pdf_printf("<%04X> <%s>\n", i, gtab[i].unicode_seq);
        } else
            pdf_printf("<%04X> <%s>\n", i, utf16be_str(gtab[i].code));
        i++;
    }
    pdf_printf("endbfchar\n");
    if (bfchar_count > 0)
        goto write_bfchar;

    /* free strings allocated by set_glyph_unicode() */
    for (i = 0; i < 65536; ++i) {
        if (gtab[i].code == UNI_EXTRA_STRING)
            xfree(gtab[i].unicode_seq);
    }

    pdf_printf("endcmap\n"
               "CMapName currentdict /CMap defineresource pop\n"
               "end\n" "end\n" "%%%%EndResource\n" "%%%%EOF\n");
    pdf_end_stream();
    return objnum;
}